inspecting-hermes-desktop-dom

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands and scripts to interact with the development environment.
  • It uses curl to verify the status of the CDP port on the local loopback address 127.0.0.1.
  • It executes local JavaScript files via node apps/desktop/scripts/eval.mjs to perform UI queries.
  • It launches isolated instances of the application using npx electron . with specific user data directories.
  • [PROMPT_INJECTION]: The skill facilitates reading live application content, which introduces a vector for indirect prompt injection if the application displays untrusted data.
  • Ingestion points: Data is retrieved from the browser context via the cdp.eval method and the scripts/eval.mjs script as described in SKILL.md.
  • Boundary markers: None detected. The instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of the DOM.
  • Capability inventory: The agent has the capability to execute shell commands (node, npx, curl) and access the local file system (via --user-data-dir and HERMES_HOME environment variables).
  • Sanitization: No explicit sanitization or filtering of the DOM content is described before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:56 AM
Security Audit — agent-trust-hub — inspecting-hermes-desktop-dom